Triple
T17880467
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Stevie |
E447069
|
entity |
| Predicate | title |
P38
|
FINISHED |
| Object | Stevie |
—
|
NE NERFINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Stevie | Statement: [Stevie, title, Stevie]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Stevie Context triple: [Stevie, title, Stevie]
-
A.
Stevie
chosen
Stevie is a common diminutive or nickname for the given name Stephen.
-
B.
Stevie
Stevie is a biographical film about British poet and playwright Stevie Smith, adapted from Hugh Whitemore’s play and starring Glenda Jackson in the title role.
-
C.
Stevie
Stevie is a compassionate yet troubled supporting character in the psychological thriller film "The Machinist," who becomes emotionally entangled with the insomniac protagonist Trevor Reznik.
-
D.
Stevie
"Stevie" is a jazz-influenced instrumental track by Yesterdays New Quintet, the Madlib-led project known for its experimental, sample-based approach to modern jazz and hip-hop.
-
E.
Stevie J
Stevie J is an American record producer and television personality best known for his influential work with Bad Boy Records in the 1990s and his appearances on the reality series "Love & Hip Hop: Atlanta."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69d8b9f4c22c819093c2680434472894 |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e49c0e56bc819097649377b520de63 |
completed | April 19, 2026, 9:10 a.m. |
Created at: April 10, 2026, 10:18 a.m.